Skip to the content.

Schedule

All times are in EST and pertain to April 29. To get links to all presentations, please login to the ICLR virtual website for this workshop.

Time Type Title
08:00 AM - 08:10 AM Live Opening Remarks
08:10 AM - 08:30 AM Live Summary of Previous Workshops
08:30 AM - 09:00 AM Foundation Talk Smita Krishnaswamy
09:00 AM - 09:30 AM Foundation Talk Bernadette Stolz
09:30 AM - 10:10 AM Panel Discussion (live) Panel D: Bridging Theory and Practice
10:10 AM - 10:30 AM Invited Talk Roland Kwitt
10:30 AM - 10:50 AM Invited Talk Stefanie Jegelka
10:50 AM - 11:00 AM Case Study Stefan Horoi
11:00 AM - 11:40 AM Panel Discussion (live) Panel C: Topology-Driven Machine Learning
11:40 AM - 11:45 AM Spotlight Neural Approximation of Extended Persistent Homology on Graphs
11:45 AM - 11:50 AM Spotlight RipsNet: a general architecture for fast and robust estimation of the persistent homology of point clouds
11:50 AM - 11:55 AM Spotlight Pre-training Molecular Graph Representation with 3D Geometry
11:55 AM - 12:00 PM Spotlight Group Symmetry in PAC Learning
12:00 PM - 01:00 PM Poster session on Gather.Town Poster Session I
01:40 PM - 01:50 PM Case Study Tara Chari
01:50 PM - 02:30 PM Panel Discussion (live) Panel A: Data-Driven Manifold Learning
02:30 PM - 02:35 PM Spotlight TopTemp: Parsing Precipitate Structure from Temper Topology
02:35 PM - 02:40 PM Spotlight A Piece-wise Polynomial Filtering Approach for Graph Neural Networks
02:40 PM - 02:45 PM Spotlight Message passing all the way up
02:45 PM - 02:50 PM Spotlight Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
02:50 PM - 03:50 PM Poster session on Gather.Town Poster Session II
03:50 PM - 04:00 PM Case Study Dmitry Kobak
04:00 PM - 04:50 PM Panel Discussion (live) Panel B: Long-Range Graph Representation Learning
04:40 PM - 04:50 PM Case Study Jessica Moore
04:50 PM - 05:00 PM Live Closing Remarks

Panel A: Data-Driven Manifold Learning

Panel B: Long-Range Graph Representation Learning

Panel C: Topology-Driven Machine Learning

Panel D: Bridging Theory and Practice